Four ways AI and machine learning will transform healthcare in 2020 -

• Read original article here

Four ways AI and machine learning will transform healthcare in 2020
January 3, 2020
From AI assisted robotic surgery to clinical diagnosis, image analysis and administrative tasks, the use of artificial intelligence and machine learning (ML) technologies is increasing within healthcare. In fact, 75% of healthcare enterprises are planning to execute an AI strategy next year, whether that’s exploring how it can automate critical but repetitive tasks to free up time for clinicians, how automatic speech recognition can speed up disease diagnosis, or how it can create synthetic controls for clinical trials. 2020 holds great opportunity to further unleash its potential.
With this in mind, we spoke to several industry experts operating in the AI and ML space for healthcare and life sciences, to explore the key trends and challenges we can expect to encounter in 2020.
More effective deployment of AI tools will become a focus
Firstly, when executing an AI strategy, organisations within the industry will start to focus to a greater extent on where AI/ML technologies can be used most effectively, and how to deploy them for maximum benefit in real clinical scenarios.
This will require careful consideration around how tools are implemented across various areas of healthcare, and for Mario Nacinovich, global head, communications & marketing at AiCure – which uses AI to see, hear and understand how patients respond to treatment – there are different challenges associated with each area.
“From a societal standpoint, building greater trust in AI and protecting personal healthcare data will continue to be among the omnipresent challenges. From an administrative standpoint, making it easier for AI to integrate with existing technology infrastructure will certainly help adoption.”
“AI will play a critical role in understanding how a drug is performing in real-time and how patients are responding in clinical research including medication adherence and their behaviour”
Mario Nacinovich
Overarchingly, though, he believes that deploying AI capabilities more effectively comes down to “ensuring that back-end processes gain greater efficiencies” in order to reduce timescales and provide better outcomes for patients.
The idea of effective deployment is also one which Eyal Gura, CEO and co-founder of Zebra Medical Vision, an imaging analytics platform which uses AI, believes will become a focus in 2020: “Having a single AI solution that integrates seamlessly into existing workflows at an affordable rate will be critical in supporting clinicians in delivering better patient care.”
As Gura explains, with two billion people joining the middle class, a rising ageing population and the growing shortage in medical experts, “AI will be critical in enabling communities to provide productive and consistent health services”.
AI will be increasingly applied to imaging diagnostics
Charles Taylor, co-founder of HeartFlow, which has developed a noninvasive test that helps clinicians to understand the severity of coronary heart disease, believes that we are only just beginning to see the full benefits of what medical imaging and AI can do for diagnostics.
“Right now, we’re able to use medical imaging and AI to give physicians unprecedented insight into potentially life-threatening restrictions on blood flow within the body,” he says. “But we’ve only just scratched the surface of what integration between information technology, computers and healthcare can achieve, and the expectations are high.”
Dr Michalis Papadakis, CEO and co-founder of Brainomix – spun out of the University of Oxford – also believes we can expect to see AI and ML “become the driving force behind imaging diagnostics”.
“With around 780,000 people suffering a stroke each year in Europe, and 7.4 million people living with heart and circulatory diseases in the UK, it is imperative we find ways to reduce the burden on healthcare organisations and improve time to disease detection.
“The number of MRI and CT scans, for example, is already on the rise, and AI has the ability to read scans as accurately as an expert physician. Utilising these new technologies to review scans for any disease can reduce patient wait time and ease the burden on medical staff. There will be greater recognition next year of the value of AI in augmenting human performance.”
Novel and digital biomarkers will support disease diagnosis
Being able to unlock new biomarkers is crucial in diagnosing diseases, and AI/ML technology has the power to enhance the use of biomarkers. One area that biomarkers are being used to great effect is in the diagnosis of Alzheimer’s and Dementia. Dr Steven Chance, CEO at Oxford Brain Diagnostics, explained that the company is focused on improving the treatment of Alzheimer’s by using ML to analyse MRI scans of the cerebral cortex, enabling early and accurate detection. He says: “Dementia remains highly complex in nature and requires extensive collaboration to succeed. Urgent action to address these challenges is needed today.”
He also explains that “unlocking new biomarkers, leveraging smarter science and deploying funds where they are needed most may give the industry a chance to defeat the terrible condition. We must re-focus our efforts and move quickly now towards examining the disease much earlier, allowing novel biomarkers to measure the progression more accurately and develop specific and targeted drug treatments for the range of dementias that exist.”
Francesca Cormack PhD, director of research & innovation at Cambridge Cognition, is also focused on digital biomarkers and the use of AI/ML for detecting neurodegenerative conditions such as Alzheimer’s.
“The upward trajectory of digital capabilities over the last decade, combined with the widespread adoption of devices, has augmented biological markers with digital measures of disease progression,” she says.
“In our field, it is now possible to use AI to enrich cognitive test scores with metrics that indicate cognitive effort, i.e. the unique features of a patient’s voice that reveal when they are finding it particularly challenging to perform a task. Patients who are ostensibly performing within normal ranges but struggling to maintain that performance are likely suffering with the early stages of decline and could benefit from interventions that might slow or prevent further neurodegeneration.
“Over the next year, we expect to see improvements in the precision of digital biomarkers for rapidly detecting neurodegenerative conditions such as Alzheimer’s disease. The ultimate goal is to integrate digital biomarkers into clinical care and improve patient outcomes.”
Clinical trials will continue to be transformed
Finally, there is huge potential for AI and ML to continue to transform clinical trials. As Mario Nacinovich explains: “Once identified and recruited, one of the biggest challenges in clinical trials is keeping subjects engaged and optimised to treatment. Medication non-adherence has been shown to increase variance, lower study power, and reduce the magnitude of treatment effects. AI will play a critical role in understanding how a drug is performing in real-time and how patients are responding in clinical research including medication adherence and their behaviour.
“The adoption of new technologies in 2020 and beyond have the potential to provide clinicians with improvements in overall patient engagement, outcomes, quality of life, practicality in use, and reduce clinical development time and associated costs.”
To conclude, Eyal Gura’s insights provide a concise summary of what we can expect to see from the AI and healthcare industries in the near future: “From medical imaging analysis to sensors and smart alerts, we are going to witness more improved and personalised care. In 2020, we will see AI in deployment of hundreds of health networks globally and impact on millions of patient lives. AI has the power to transform patient care and empower radiologists to help with patient diagnosis.”